github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-22 14:49:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

🐛 fix: missing kwargs in from_agent_and_tools in dataframe agent (#2285)

Browse Source 
Hello! 
I've noticed a bug in `create_pandas_dataframe_agent`. When calling it
with argument `return_intermediate_steps=True`, it doesn't return the
intermediate step. I think the issue is that `kwargs` was not passed
where it needed to be passed. It should be passed into
`AgentExecutor.from_agent_and_tools`

Please correct me if my solution isn't appropriate and I will fix with
the appropriate approach.

Co-authored-by: alhajji <m.alhajji@drahim.sa>
This commit is contained in:
MohammedAlhajji 2023-04-04 00:26:03 +03:00 committed by GitHub
parent 3fb4997ad8
commit fd0d631f39
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
langchain/agents/agent_toolkits/pandas/base.py
View File

@ -18,6 +18,9 @@ def create_pandas_dataframe_agent(
suffix: str = SUFFIX, suffix: str = SUFFIX,
input_variables: Optional[List[str]] = None, input_variables: Optional[List[str]] = None,
verbose: bool = False, verbose: bool = False,
return_intermediate_steps: bool = False,
max_iterations: Optional[int] = 15,
early_stopping_method: str = "force",
**kwargs: Any, **kwargs: Any,
) -> AgentExecutor: ) -> AgentExecutor:
"""Construct a pandas agent from an LLM and dataframe.""" """Construct a pandas agent from an LLM and dataframe."""
@ -39,4 +42,11 @@ def create_pandas_dataframe_agent(
) )
tool_names = [tool.name for tool in tools] tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs) agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=verbose) return AgentExecutor.from_agent_and_tools(
agent=agent,
tools=tools,
verbose=verbose,
return_intermediate_steps=return_intermediate_steps,
max_iterations=max_iterations,
early_stopping_method=early_stopping_method,
)